Search Results for author:
Found 3 papers, 2 papers with code
EdgePruner: Poisoned Edge Pruning in Graph Contrastive Learning
We focus on the fact that the state-of-the-art poisoning attack on GCL tends to mainly add adversarial edges to create poisoned graphs, which means that pruning edges is important to sanitize the graphs.
VoteTRANS: Detecting Adversarial Text without Training by Voting on Hard Labels of Transformations
Specifically, VoteTRANS detects adversarial text by comparing the hard labels of input text and its transformation.
SEPP: Similarity Estimation of Predicted Probabilities for Defending and Detecting Adversarial Text
In terms of misclassified texts, a classifier handles the texts with both incorrect predictions and adversarial texts, which are generated to fool the classifier, which is called a victim.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
